weco 0.2.3__tar.gz → 0.2.5__tar.gz

{weco-0.2.3 → weco-0.2.5}/.github/workflows/release.yml

@@ -90,7 +90,7 @@ jobs:
         GITHUB_TOKEN: ${{ github.token }}
       run: >-
         gh release create
-        'v0.2.3'
+        'v0.2.5'
         --repo '${{ github.repository }}'
         --notes ""
 
@@ -102,5 +102,5 @@ jobs:
       # sigstore-produced signatures and certificates.
       run: >-
         gh release upload
-        'v0.2.3' dist/**
+        'v0.2.5' dist/**
         --repo '${{ github.repository }}'

weco-0.2.5/PKG-INFO

@@ -0,0 +1,189 @@
+Metadata-Version: 2.4
+Name: weco
+Version: 0.2.5
+Summary: Documentation for `weco`, a CLI for using Weco AI's code optimizer.
+Author-email: Weco AI Team <dhruv@weco.ai>
+License: MIT
+Project-URL: Homepage, https://github.com/WecoAI/weco-cli
+Keywords: AI,Code Optimization,Code Generation
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: License :: OSI Approved :: MIT License
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: rich
+Provides-Extra: dev
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: setuptools_scm; extra == "dev"
+Dynamic: license-file
+
+# Weco CLI – Code Optimizer for Machine Learning Engineers
+
+[![Python](https://img.shields.io/badge/Python-3.12.0-blue)](https://www.python.org)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
+[![PyPI version](https://badge.fury.io/py/weco.svg)](https://badge.fury.io/py/weco)
+
+`weco` is a command-line interface for interacting with Weco AI's code optimizer, powered by [AI-Driven Exploration](https://arxiv.org/abs/2502.13138). It helps you automate the improvement of your code for tasks like GPU kernel optimization, feature engineering, model development, and prompt engineering.
+
+https://github.com/user-attachments/assets/cb724ef1-bff6-4757-b457-d3b2201ede81
+
+---
+
+## Overview
+
+The `weco` CLI leverages a tree search approach guided by Large Language Models (LLMs) to iteratively explore and refine your code. It automatically applies changes, runs your evaluation script, parses the results, and proposes further improvements based on the specified goal.
+
+![image](https://github.com/user-attachments/assets/a6ed63fa-9c40-498e-aa98-a873e5786509)
+
+---
+
+## Example Use Cases
+
+Here's how `weco` can be applied to common ML engineering tasks:
+
+*   **GPU Kernel Optimization:**
+    *   **Goal:** Improve the speed or efficiency of low-level GPU code.
+    *   **How:** `weco` iteratively refines CUDA, Triton, Metal, or other kernel code specified in your `--source` file.
+    *   **`--eval-command`:** Typically runs a script that compiles the kernel, executes it, and benchmarks performance (e.g., latency, throughput).
+    *   **`--metric`:** Examples include `latency`, `throughput`, `TFLOPS`, `memory_bandwidth`. Optimize to `minimize` latency or `maximize` throughput.
+
+*   **Feature Engineering:**
+    *   **Goal:** Discover better data transformations or feature combinations for your machine learning models.
+    *   **How:** `weco` explores different processing steps or parameters within your feature transformation code (`--source`).
+    *   **`--eval-command`:** Executes a script that applies the features, trains/validates a model using those features, and prints a performance score.
+    *   **`--metric`:** Examples include `accuracy`, `AUC`, `F1-score`, `validation_loss`. Usually optimized to `maximize` accuracy/AUC/F1 or `minimize` loss.
+
+*   **Model Development:**
+    *   **Goal:** Tune hyperparameters or experiment with small architectural changes directly within your model's code.
+    *   **How:** `weco` modifies hyperparameter values (like learning rate, layer sizes if defined in the code) or structural elements in your model definition (`--source`).
+    *   **`--eval-command`:** Runs your model training and evaluation script, printing the key performance indicator.
+    *   **`--metric`:** Examples include `validation_accuracy`, `test_loss`, `inference_time`, `perplexity`. Optimize according to the metric's nature (e.g., `maximize` accuracy, `minimize` loss).
+
+*   **Prompt Engineering:**
+    *   **Goal:** Refine prompts used within larger systems (e.g., for LLM interactions) to achieve better or more consistent outputs.
+    *   **How:** `weco` modifies prompt templates, examples, or instructions stored in the `--source` file.
+    *   **`--eval-command`:** Executes a script that uses the prompt, generates an output, evaluates that output against desired criteria (e.g., using another LLM, checking for keywords, format validation), and prints a score.
+    *   **`--metric`:** Examples include `quality_score`, `relevance`, `task_success_rate`, `format_adherence`. Usually optimized to `maximize`.
+
+---
+
+
+## Setup
+
+1.  **Install the Package:**
+
+    ```bash
+    pip install weco
+    ```
+
+2.  **Configure API Keys:**
+
+    Set the appropriate environment variables for your desired language model provider:
+
+    -   **OpenAI:** `export OPENAI_API_KEY="your_key_here"`
+    -   **Anthropic:** `export ANTHROPIC_API_KEY="your_key_here"`
+    -   **Google DeepMind:** `export GEMINI_API_KEY="your_key_here"` (Google AI Studio has a free API usage quota. Create a key [here](https://aistudio.google.com/apikey) to use weco for free.)
+
+---
+
+## Usage
+<div style="background-color: #fff3cd; border: 1px solid #ffeeba; padding: 15px; border-radius: 4px; margin-bottom: 15px;">
+  <strong>⚠️ Warning: Code Modification</strong><br>
+  <code>weco</code> directly modifies the file specified by <code>--source</code> during the optimization process. It is <strong>strongly recommended</strong> to use version control (like Git) to track changes and revert if needed. Alternatively, ensure you have a backup of your original file before running the command. Upon completion, the file will contain the best-performing version of the code found during the run.
+</div>
+
+---
+
+### Examples
+
+**Example 1: Optimizing PyTorch operations**
+
+```bash
+weco --source examples/simple-torch/optimize.py \
+     --eval-command "python examples/simple-torch/evaluate.py --solution-path examples/simple-torch/optimize.py --device mps" \
+     --metric speedup \
+     --maximize true \
+     --steps 15 \
+     --model o3-mini \
+     --additional-instructions "Fuse operations in the forward method while ensuring the max float deviation remains small. Maintain the same format of the code."
+```
+
+**Example 2: Optimizing MLX operations with instructions from a file**
+
+Sometimes, additional context or instructions are too complex for a single command-line string. You can provide a path to a file containing these instructions.
+
+```bash
+weco --source examples/simple-mlx/optimize.py \
+     --eval-command "python examples/simple-mlx/evaluate.py --solution-path examples/simple-mlx/optimize.py" \
+     --metric speedup \
+     --maximize true \
+     --steps 30 \
+     --model o3-mini \
+     --additional-instructions examples/simple-mlx/metal-examples.rst
+```
+
+---
+
+### Command Line Arguments
+
+| Argument                    | Description                                                                                                                                                              | Required |
+| :-------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- |
+| `--source`                  | Path to the source code file that will be optimized (e.g., `optimize.py`).                                                                                               | Yes      |
+| `--eval-command`            | Command to run for evaluating the code in `--source`. This command should print the target `--metric` and its value to the terminal (stdout/stderr). See note below. | Yes      |
+| `--metric`                  | The name of the metric you want to optimize (e.g., 'accuracy', 'speedup', 'loss'). This metric name should match what's printed by your `--eval-command`.            | Yes      |
+| `--maximize`                | Whether to maximize (`true`) or minimize (`false`) the metric.                                                                                                           | Yes      |
+| `--steps`                   | Number of optimization steps (LLM iterations) to run.                                                                                                                    | Yes      |
+| `--model`                   | Model identifier for the LLM to use (e.g., `gpt-4o`, `claude-3.5-sonnet`). Recommended models to try include `o3-mini`, `claude-3-haiku`, and `gemini-2.5-pro-exp-03-25`.        | Yes      |
+| `--additional-instructions` | (Optional) Natural language description of specific instructions OR path to a file containing detailed instructions to guide the LLM.                                       | No       |
+
+---
+
+
+
+### Important Note on Evaluation
+
+The command specified by `--eval-command` is crucial. It's responsible for executing the potentially modified code from `--source` and assessing its performance. **This command MUST print the metric you specified with `--metric` along with its numerical value to the terminal (standard output or standard error).** Weco reads this output to understand how well each code version performs and guide the optimization process.
+
+For example, if you set `--metric speedup`, your evaluation script (`eval.py` in the examples) should output a line like:
+
+```
+speedup: 1.5
+```
+
+or
+
+```
+Final speedup value = 1.5
+```
+
+Weco will parse this output to extract the numerical value (1.5 in this case) associated with the metric name ('speedup').
+
+
+## Contributing
+
+We welcome contributions! To get started:
+
+1.  **Fork and Clone the Repository:**
+    ```bash
+    git clone https://github.com/WecoAI/weco-cli.git
+    cd weco-cli
+    ```
+
+2.  **Install Development Dependencies:**
+    ```bash
+    pip install -e ".[dev]"
+    ```
+
+3.  **Create a Feature Branch:**
+    ```bash
+    git checkout -b feature/your-feature-name
+    ```
+
+4.  **Make Your Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
+
+5.  **Commit and Push** your changes, then open a pull request with a clear description of your enhancements.
+
+---

weco-0.2.5/README.md

@@ -0,0 +1,167 @@
+# Weco CLI – Code Optimizer for Machine Learning Engineers
+
+[![Python](https://img.shields.io/badge/Python-3.12.0-blue)](https://www.python.org)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
+[![PyPI version](https://badge.fury.io/py/weco.svg)](https://badge.fury.io/py/weco)
+
+`weco` is a command-line interface for interacting with Weco AI's code optimizer, powered by [AI-Driven Exploration](https://arxiv.org/abs/2502.13138). It helps you automate the improvement of your code for tasks like GPU kernel optimization, feature engineering, model development, and prompt engineering.
+
+https://github.com/user-attachments/assets/cb724ef1-bff6-4757-b457-d3b2201ede81
+
+---
+
+## Overview
+
+The `weco` CLI leverages a tree search approach guided by Large Language Models (LLMs) to iteratively explore and refine your code. It automatically applies changes, runs your evaluation script, parses the results, and proposes further improvements based on the specified goal.
+
+![image](https://github.com/user-attachments/assets/a6ed63fa-9c40-498e-aa98-a873e5786509)
+
+---
+
+## Example Use Cases
+
+Here's how `weco` can be applied to common ML engineering tasks:
+
+*   **GPU Kernel Optimization:**
+    *   **Goal:** Improve the speed or efficiency of low-level GPU code.
+    *   **How:** `weco` iteratively refines CUDA, Triton, Metal, or other kernel code specified in your `--source` file.
+    *   **`--eval-command`:** Typically runs a script that compiles the kernel, executes it, and benchmarks performance (e.g., latency, throughput).
+    *   **`--metric`:** Examples include `latency`, `throughput`, `TFLOPS`, `memory_bandwidth`. Optimize to `minimize` latency or `maximize` throughput.
+
+*   **Feature Engineering:**
+    *   **Goal:** Discover better data transformations or feature combinations for your machine learning models.
+    *   **How:** `weco` explores different processing steps or parameters within your feature transformation code (`--source`).
+    *   **`--eval-command`:** Executes a script that applies the features, trains/validates a model using those features, and prints a performance score.
+    *   **`--metric`:** Examples include `accuracy`, `AUC`, `F1-score`, `validation_loss`. Usually optimized to `maximize` accuracy/AUC/F1 or `minimize` loss.
+
+*   **Model Development:**
+    *   **Goal:** Tune hyperparameters or experiment with small architectural changes directly within your model's code.
+    *   **How:** `weco` modifies hyperparameter values (like learning rate, layer sizes if defined in the code) or structural elements in your model definition (`--source`).
+    *   **`--eval-command`:** Runs your model training and evaluation script, printing the key performance indicator.
+    *   **`--metric`:** Examples include `validation_accuracy`, `test_loss`, `inference_time`, `perplexity`. Optimize according to the metric's nature (e.g., `maximize` accuracy, `minimize` loss).
+
+*   **Prompt Engineering:**
+    *   **Goal:** Refine prompts used within larger systems (e.g., for LLM interactions) to achieve better or more consistent outputs.
+    *   **How:** `weco` modifies prompt templates, examples, or instructions stored in the `--source` file.
+    *   **`--eval-command`:** Executes a script that uses the prompt, generates an output, evaluates that output against desired criteria (e.g., using another LLM, checking for keywords, format validation), and prints a score.
+    *   **`--metric`:** Examples include `quality_score`, `relevance`, `task_success_rate`, `format_adherence`. Usually optimized to `maximize`.
+
+---
+
+
+## Setup
+
+1.  **Install the Package:**
+
+    ```bash
+    pip install weco
+    ```
+
+2.  **Configure API Keys:**
+
+    Set the appropriate environment variables for your desired language model provider:
+
+    -   **OpenAI:** `export OPENAI_API_KEY="your_key_here"`
+    -   **Anthropic:** `export ANTHROPIC_API_KEY="your_key_here"`
+    -   **Google DeepMind:** `export GEMINI_API_KEY="your_key_here"` (Google AI Studio has a free API usage quota. Create a key [here](https://aistudio.google.com/apikey) to use weco for free.)
+
+---
+
+## Usage
+<div style="background-color: #fff3cd; border: 1px solid #ffeeba; padding: 15px; border-radius: 4px; margin-bottom: 15px;">
+  <strong>⚠️ Warning: Code Modification</strong><br>
+  <code>weco</code> directly modifies the file specified by <code>--source</code> during the optimization process. It is <strong>strongly recommended</strong> to use version control (like Git) to track changes and revert if needed. Alternatively, ensure you have a backup of your original file before running the command. Upon completion, the file will contain the best-performing version of the code found during the run.
+</div>
+
+---
+
+### Examples
+
+**Example 1: Optimizing PyTorch operations**
+
+```bash
+weco --source examples/simple-torch/optimize.py \
+     --eval-command "python examples/simple-torch/evaluate.py --solution-path examples/simple-torch/optimize.py --device mps" \
+     --metric speedup \
+     --maximize true \
+     --steps 15 \
+     --model o3-mini \
+     --additional-instructions "Fuse operations in the forward method while ensuring the max float deviation remains small. Maintain the same format of the code."
+```
+
+**Example 2: Optimizing MLX operations with instructions from a file**
+
+Sometimes, additional context or instructions are too complex for a single command-line string. You can provide a path to a file containing these instructions.
+
+```bash
+weco --source examples/simple-mlx/optimize.py \
+     --eval-command "python examples/simple-mlx/evaluate.py --solution-path examples/simple-mlx/optimize.py" \
+     --metric speedup \
+     --maximize true \
+     --steps 30 \
+     --model o3-mini \
+     --additional-instructions examples/simple-mlx/metal-examples.rst
+```
+
+---
+
+### Command Line Arguments
+
+| Argument                    | Description                                                                                                                                                              | Required |
+| :-------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- |
+| `--source`                  | Path to the source code file that will be optimized (e.g., `optimize.py`).                                                                                               | Yes      |
+| `--eval-command`            | Command to run for evaluating the code in `--source`. This command should print the target `--metric` and its value to the terminal (stdout/stderr). See note below. | Yes      |
+| `--metric`                  | The name of the metric you want to optimize (e.g., 'accuracy', 'speedup', 'loss'). This metric name should match what's printed by your `--eval-command`.            | Yes      |
+| `--maximize`                | Whether to maximize (`true`) or minimize (`false`) the metric.                                                                                                           | Yes      |
+| `--steps`                   | Number of optimization steps (LLM iterations) to run.                                                                                                                    | Yes      |
+| `--model`                   | Model identifier for the LLM to use (e.g., `gpt-4o`, `claude-3.5-sonnet`). Recommended models to try include `o3-mini`, `claude-3-haiku`, and `gemini-2.5-pro-exp-03-25`.        | Yes      |
+| `--additional-instructions` | (Optional) Natural language description of specific instructions OR path to a file containing detailed instructions to guide the LLM.                                       | No       |
+
+---
+
+
+
+### Important Note on Evaluation
+
+The command specified by `--eval-command` is crucial. It's responsible for executing the potentially modified code from `--source` and assessing its performance. **This command MUST print the metric you specified with `--metric` along with its numerical value to the terminal (standard output or standard error).** Weco reads this output to understand how well each code version performs and guide the optimization process.
+
+For example, if you set `--metric speedup`, your evaluation script (`eval.py` in the examples) should output a line like:
+
+```
+speedup: 1.5
+```
+
+or
+
+```
+Final speedup value = 1.5
+```
+
+Weco will parse this output to extract the numerical value (1.5 in this case) associated with the metric name ('speedup').
+
+
+## Contributing
+
+We welcome contributions! To get started:
+
+1.  **Fork and Clone the Repository:**
+    ```bash
+    git clone https://github.com/WecoAI/weco-cli.git
+    cd weco-cli
+    ```
+
+2.  **Install Development Dependencies:**
+    ```bash
+    pip install -e ".[dev]"
+    ```
+
+3.  **Create a Feature Branch:**
+    ```bash
+    git checkout -b feature/your-feature-name
+    ```
+
+4.  **Make Your Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
+
+5.  **Commit and Push** your changes, then open a pull request with a clear description of your enhancements.
+
+---

{weco-0.2.3 → weco-0.2.5}/examples/simple-mlx/evaluate.py

@@ -66,7 +66,7 @@ def bench(f, inputs, n_warmup, n_rep):
     t_avg = 0.0
     for _ in range(n_rep):
         # Clear cache before timing
-        mx.metal.clear_cache()
+        mx.clear_cache()
 
         start_time = time.time()
         result = f(inputs)

{weco-0.2.3 → weco-0.2.5}/pyproject.toml

@@ -10,7 +10,7 @@ authors = [
 ]
 description = "Documentation for `weco`, a CLI for using Weco AI's code optimizer."
 readme = "README.md"
-version = "0.2.3"
+version = "0.2.5"
 license = {text = "MIT"}
 requires-python = ">=3.12"
 dependencies = ["requests", "rich"]

{weco-0.2.3 → weco-0.2.5}/weco/__init__.py

@@ -1,4 +1,4 @@
 # DO NOT EDIT
-__pkg_version__ = "0.2.3"
+__pkg_version__ = "0.2.5"
 __api_version__ = "v1"
 __base_url__ = f"https://api.aide.weco.ai/{__api_version__}"

{weco-0.2.3 → weco-0.2.5}/weco/api.py

@@ -29,6 +29,7 @@ def start_optimization_session(
     search_policy_config: Dict[str, Any],
     additional_instructions: str = None,
     api_keys: Dict[str, Any] = {},
+    timeout: int = 800,
 ) -> Dict[str, Any]:
     """Start the optimization session."""
     with console.status("[bold green]Starting Optimization..."):
@@ -47,6 +48,7 @@ def start_optimization_session(
                     },
                     "metadata": {"client_name": "cli", "client_version": __pkg_version__, **api_keys},
                 },
+                timeout=timeout,
             )
             response.raise_for_status()
             return response.json()
@@ -60,6 +62,7 @@ def evaluate_feedback_then_suggest_next_solution(
     execution_output: str,
     additional_instructions: str = None,
     api_keys: Dict[str, Any] = {},
+    timeout: int = 800,
 ) -> Dict[str, Any]:
     """Evaluate the feedback and suggest the next solution."""
     try:
@@ -70,6 +73,7 @@ def evaluate_feedback_then_suggest_next_solution(
                 "additional_instructions": additional_instructions,
                 "metadata": {**api_keys},
             },
+            timeout=timeout,
         )
         response.raise_for_status()
         return response.json()
@@ -78,11 +82,13 @@ def evaluate_feedback_then_suggest_next_solution(
 
 
 def get_optimization_session_status(
-    console: rich.console.Console, session_id: str, include_history: bool = False
+    console: rich.console.Console, session_id: str, include_history: bool = False, timeout: int = 800
 ) -> Dict[str, Any]:
     """Get the current status of the optimization session."""
     try:
-        response = requests.get(f"{__base_url__}/sessions/{session_id}", params={"include_history": include_history})
+        response = requests.get(
+            f"{__base_url__}/sessions/{session_id}", params={"include_history": include_history}, timeout=timeout
+        )
         response.raise_for_status()
         return response.json()
     except requests.exceptions.HTTPError as e:

{weco-0.2.3 → weco-0.2.5}/weco/cli.py

@@ -79,6 +79,8 @@ def main() -> None:
             source_code = read_from_path(fp=source_fp, is_json=False)
             # Read API keys
             api_keys = read_api_keys_from_env()
+            # API request timeout
+            timeout = 800
 
         # Initialize panels
         summary_panel = SummaryPanel(maximize=maximize, metric_name=metric_name, total_steps=steps, model=args.model)
@@ -102,56 +104,62 @@ def main() -> None:
             search_policy_config=search_policy_config,
             additional_instructions=additional_instructions,
             api_keys=api_keys,
+            timeout=timeout,
         )
 
-        # Define the runs directory (.runs/<session-id>)
-        session_id = session_response["session_id"]
-        runs_dir = pathlib.Path(".runs") / session_id
-        runs_dir.mkdir(parents=True, exist_ok=True)
-
-        # Save the original code (.runs/<session-id>/original.py)
-        runs_copy_source_fp = runs_dir / "original.py"
-        write_to_path(fp=runs_copy_source_fp, content=source_code)
-
-        # Write the code string to the source file path
-        # Do this after the original code is saved
-        write_to_path(fp=source_fp, content=session_response["code"])
-
-        # Update the panels with the initial solution
-        # Add session id now that we have it
-        summary_panel.session_id = session_id
-        # Set the step of the progress bar
-        summary_panel.set_step(step=0)
-        # Update the token counts
-        summary_panel.update_token_counts(usage=session_response["usage"])
-        # Update the plan
-        plan_panel.update(plan=session_response["plan"])
-        # Build the metric tree
-        tree_panel.build_metric_tree(
-            nodes=[
-                {
-                    "solution_id": session_response["solution_id"],
-                    "parent_id": None,
-                    "code": session_response["code"],
-                    "step": 0,
-                    "metric_value": None,
-                    "is_buggy": False,
-                }
-            ]
-        )
-        # Set the current solution as unevaluated since we haven't run the evaluation function and fed it back to the model yet
-        tree_panel.set_unevaluated_node(node_id=session_response["solution_id"])
-        # Update the solution panels with the initial solution and get the panel displays
-        solution_panels.update(
-            current_node=Node(
-                id=session_response["solution_id"], parent_id=None, code=session_response["code"], metric=None, is_buggy=False
-            ),
-            best_node=None,
-        )
-        current_solution_panel, best_solution_panel = solution_panels.get_display(current_step=0)
         # Define the refresh rate
         refresh_rate = 4
         with Live(layout, refresh_per_second=refresh_rate, screen=True) as live:
+            # Define the runs directory (.runs/<session-id>)
+            session_id = session_response["session_id"]
+            runs_dir = pathlib.Path(".runs") / session_id
+            runs_dir.mkdir(parents=True, exist_ok=True)
+
+            # Save the original code (.runs/<session-id>/original.py)
+            runs_copy_source_fp = runs_dir / "original.py"
+            write_to_path(fp=runs_copy_source_fp, content=source_code)
+
+            # Write the code string to the source file path
+            # Do this after the original code is saved
+            write_to_path(fp=source_fp, content=session_response["code"])
+
+            # Update the panels with the initial solution
+            # Add session id now that we have it
+            summary_panel.session_id = session_id
+            # Set the step of the progress bar
+            summary_panel.set_step(step=0)
+            # Update the token counts
+            summary_panel.update_token_counts(usage=session_response["usage"])
+            # Update the plan
+            plan_panel.update(plan=session_response["plan"])
+            # Build the metric tree
+            tree_panel.build_metric_tree(
+                nodes=[
+                    {
+                        "solution_id": session_response["solution_id"],
+                        "parent_id": None,
+                        "code": session_response["code"],
+                        "step": 0,
+                        "metric_value": None,
+                        "is_buggy": False,
+                    }
+                ]
+            )
+            # Set the current solution as unevaluated since we haven't run the evaluation function and fed it back to the model yet
+            tree_panel.set_unevaluated_node(node_id=session_response["solution_id"])
+            # Update the solution panels with the initial solution and get the panel displays
+            solution_panels.update(
+                current_node=Node(
+                    id=session_response["solution_id"],
+                    parent_id=None,
+                    code=session_response["code"],
+                    metric=None,
+                    is_buggy=False,
+                ),
+                best_node=None,
+            )
+            current_solution_panel, best_solution_panel = solution_panels.get_display(current_step=0)
+
             # Update the entire layout
             smooth_update(
                 live=live,
@@ -187,6 +195,7 @@ def main() -> None:
                     execution_output=term_out,
                     additional_instructions=additional_instructions,
                     api_keys=api_keys,
+                    timeout=timeout,
                 )
                 # Save next solution (.runs/<session-id>/step_<step>.py)
                 write_to_path(fp=runs_dir / f"step_{step}.py", content=eval_and_next_solution_response["code"])
@@ -196,7 +205,9 @@ def main() -> None:
 
                 # Get the optimization session status for
                 # the best solution, its score, and the history to plot the tree
-                status_response = get_optimization_session_status(console=console, session_id=session_id, include_history=True)
+                status_response = get_optimization_session_status(
+                    console=console, session_id=session_id, include_history=True, timeout=timeout
+                )
 
                 # Update the step of the progress bar
                 summary_panel.set_step(step=step)
@@ -276,6 +287,7 @@ def main() -> None:
                 execution_output=term_out,
                 additional_instructions=additional_instructions,
                 api_keys=api_keys,
+                timeout=timeout,
             )
 
             # Update the progress bar
@@ -285,7 +297,9 @@ def main() -> None:
             # No need to update the plan panel since we have finished the optimization
             # Get the optimization session status for
             # the best solution, its score, and the history to plot the tree
-            status_response = get_optimization_session_status(console=console, session_id=session_id, include_history=True)
+            status_response = get_optimization_session_status(
+                console=console, session_id=session_id, include_history=True, timeout=timeout
+            )
             # Build the metric tree
             tree_panel.build_metric_tree(nodes=status_response["history"])
             # No need to set any solution to unevaluated since we have finished the optimization

{weco-0.2.3 → weco-0.2.5}/weco/panels.py

@@ -12,7 +12,7 @@ class SummaryPanel:
     """Holds a summary of the optimization session."""
 
     def __init__(self, maximize: bool, metric_name: str, total_steps: int, model: str, session_id: str = None):
-        self.goal = ("Maximizing" if maximize else "Minimizing") + f" {metric_name}"
+        self.goal = ("Maximizing" if maximize else "Minimizing") + f" {metric_name}..."
         self.total_input_tokens = 0
         self.total_output_tokens = 0
         self.total_steps = total_steps
@@ -48,10 +48,10 @@ class SummaryPanel:
         summary_table.add_row("")
         # Log directory
         runs_dir = f".runs/{self.session_id}"
-        summary_table.add_row(f"[bold cyan]Logs:[/] [blue]{runs_dir}[/]")
+        summary_table.add_row(f"[bold cyan]Logs:[/] [blue underline]{runs_dir}[/]")
         summary_table.add_row("")
         # Model used
-        summary_table.add_row(f"[bold cyan]Model:[/] {self.model}")
+        summary_table.add_row(f"[bold cyan]Model:[/] [yellow]{self.model}[/]")
         summary_table.add_row("")
         # Token counts
         summary_table.add_row(
@@ -197,7 +197,7 @@ class MetricTreePanel:
                     # best node
                     color = "green"
                     style = "bold"
-                    text = f"🏆 {node.metric:.3f}"
+                    text = f"{node.metric:.3f} 🏆"
                 elif node.metric is None:
                     # metric not extracted from evaluated solution
                     color = "yellow"
@@ -214,7 +214,7 @@ class MetricTreePanel:
             for child in node.children:
                 append_rec(child, subtree)
 
-        tree = Tree("solutions")
+        tree = Tree("🌳")
         for n in self.metric_tree.get_draft_nodes():
             append_rec(n, tree)
 
@@ -223,7 +223,9 @@ class MetricTreePanel:
     def get_display(self) -> Panel:
         """Get a panel displaying the solution tree."""
         # Make sure the metric tree is built before calling build_rich_tree
-        return Panel(self._build_rich_tree(), title="[bold]🌳 Exploring...", border_style="green", expand=True, padding=(0, 1))
+        return Panel(
+            self._build_rich_tree(), title="[bold]🔎 Exploring Solutions...", border_style="green", expand=True, padding=(0, 1)
+        )
 
 
 class EvaluationOutputPanel:
@@ -242,7 +244,7 @@ class EvaluationOutputPanel:
 
     def get_display(self) -> Panel:
         """Create a panel displaying the evaluation output with truncation if needed."""
-        return Panel(self.output, title="[bold]📋 Evaluation Output", border_style="red", expand=True, padding=(0, 1))
+        return Panel(self.output, title="[bold]📋 Evaluation Output", border_style="blue", expand=True, padding=(0, 1))
 
 
 class SolutionPanels:

{weco-0.2.3 → weco-0.2.5}/weco/utils.py

@@ -28,10 +28,14 @@ def read_additional_instructions(additional_instructions: str | None) -> str | N
 
     # Try interpreting as a path first
     potential_path = pathlib.Path(additional_instructions)
-    if potential_path.exists() and potential_path.is_file():
-        return read_from_path(potential_path, is_json=False)  # type: ignore # read_from_path returns str when is_json=False
-    else:
-        # If it's not a valid file path, return the string itself
+    try:
+        if potential_path.exists() and potential_path.is_file():
+            return read_from_path(potential_path, is_json=False)  # type: ignore # read_from_path returns str when is_json=False
+        else:
+            # If it's not a valid file path, return the string itself
+            return additional_instructions
+    except OSError:
+        # If the path can't be read, return the string itself
         return additional_instructions
 
 

weco-0.2.5/weco.egg-info/PKG-INFO

@@ -0,0 +1,189 @@
+Metadata-Version: 2.4
+Name: weco
+Version: 0.2.5
+Summary: Documentation for `weco`, a CLI for using Weco AI's code optimizer.
+Author-email: Weco AI Team <dhruv@weco.ai>
+License: MIT
+Project-URL: Homepage, https://github.com/WecoAI/weco-cli
+Keywords: AI,Code Optimization,Code Generation
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: License :: OSI Approved :: MIT License
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: rich
+Provides-Extra: dev
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: setuptools_scm; extra == "dev"
+Dynamic: license-file
+
+# Weco CLI – Code Optimizer for Machine Learning Engineers
+
+[![Python](https://img.shields.io/badge/Python-3.12.0-blue)](https://www.python.org)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
+[![PyPI version](https://badge.fury.io/py/weco.svg)](https://badge.fury.io/py/weco)
+
+`weco` is a command-line interface for interacting with Weco AI's code optimizer, powered by [AI-Driven Exploration](https://arxiv.org/abs/2502.13138). It helps you automate the improvement of your code for tasks like GPU kernel optimization, feature engineering, model development, and prompt engineering.
+
+https://github.com/user-attachments/assets/cb724ef1-bff6-4757-b457-d3b2201ede81
+
+---
+
+## Overview
+
+The `weco` CLI leverages a tree search approach guided by Large Language Models (LLMs) to iteratively explore and refine your code. It automatically applies changes, runs your evaluation script, parses the results, and proposes further improvements based on the specified goal.
+
+![image](https://github.com/user-attachments/assets/a6ed63fa-9c40-498e-aa98-a873e5786509)
+
+---
+
+## Example Use Cases
+
+Here's how `weco` can be applied to common ML engineering tasks:
+
+*   **GPU Kernel Optimization:**
+    *   **Goal:** Improve the speed or efficiency of low-level GPU code.
+    *   **How:** `weco` iteratively refines CUDA, Triton, Metal, or other kernel code specified in your `--source` file.
+    *   **`--eval-command`:** Typically runs a script that compiles the kernel, executes it, and benchmarks performance (e.g., latency, throughput).
+    *   **`--metric`:** Examples include `latency`, `throughput`, `TFLOPS`, `memory_bandwidth`. Optimize to `minimize` latency or `maximize` throughput.
+
+*   **Feature Engineering:**
+    *   **Goal:** Discover better data transformations or feature combinations for your machine learning models.
+    *   **How:** `weco` explores different processing steps or parameters within your feature transformation code (`--source`).
+    *   **`--eval-command`:** Executes a script that applies the features, trains/validates a model using those features, and prints a performance score.
+    *   **`--metric`:** Examples include `accuracy`, `AUC`, `F1-score`, `validation_loss`. Usually optimized to `maximize` accuracy/AUC/F1 or `minimize` loss.
+
+*   **Model Development:**
+    *   **Goal:** Tune hyperparameters or experiment with small architectural changes directly within your model's code.
+    *   **How:** `weco` modifies hyperparameter values (like learning rate, layer sizes if defined in the code) or structural elements in your model definition (`--source`).
+    *   **`--eval-command`:** Runs your model training and evaluation script, printing the key performance indicator.
+    *   **`--metric`:** Examples include `validation_accuracy`, `test_loss`, `inference_time`, `perplexity`. Optimize according to the metric's nature (e.g., `maximize` accuracy, `minimize` loss).
+
+*   **Prompt Engineering:**
+    *   **Goal:** Refine prompts used within larger systems (e.g., for LLM interactions) to achieve better or more consistent outputs.
+    *   **How:** `weco` modifies prompt templates, examples, or instructions stored in the `--source` file.
+    *   **`--eval-command`:** Executes a script that uses the prompt, generates an output, evaluates that output against desired criteria (e.g., using another LLM, checking for keywords, format validation), and prints a score.
+    *   **`--metric`:** Examples include `quality_score`, `relevance`, `task_success_rate`, `format_adherence`. Usually optimized to `maximize`.
+
+---
+
+
+## Setup
+
+1.  **Install the Package:**
+
+    ```bash
+    pip install weco
+    ```
+
+2.  **Configure API Keys:**
+
+    Set the appropriate environment variables for your desired language model provider:
+
+    -   **OpenAI:** `export OPENAI_API_KEY="your_key_here"`
+    -   **Anthropic:** `export ANTHROPIC_API_KEY="your_key_here"`
+    -   **Google DeepMind:** `export GEMINI_API_KEY="your_key_here"` (Google AI Studio has a free API usage quota. Create a key [here](https://aistudio.google.com/apikey) to use weco for free.)
+
+---
+
+## Usage
+<div style="background-color: #fff3cd; border: 1px solid #ffeeba; padding: 15px; border-radius: 4px; margin-bottom: 15px;">
+  <strong>⚠️ Warning: Code Modification</strong><br>
+  <code>weco</code> directly modifies the file specified by <code>--source</code> during the optimization process. It is <strong>strongly recommended</strong> to use version control (like Git) to track changes and revert if needed. Alternatively, ensure you have a backup of your original file before running the command. Upon completion, the file will contain the best-performing version of the code found during the run.
+</div>
+
+---
+
+### Examples
+
+**Example 1: Optimizing PyTorch operations**
+
+```bash
+weco --source examples/simple-torch/optimize.py \
+     --eval-command "python examples/simple-torch/evaluate.py --solution-path examples/simple-torch/optimize.py --device mps" \
+     --metric speedup \
+     --maximize true \
+     --steps 15 \
+     --model o3-mini \
+     --additional-instructions "Fuse operations in the forward method while ensuring the max float deviation remains small. Maintain the same format of the code."
+```
+
+**Example 2: Optimizing MLX operations with instructions from a file**
+
+Sometimes, additional context or instructions are too complex for a single command-line string. You can provide a path to a file containing these instructions.
+
+```bash
+weco --source examples/simple-mlx/optimize.py \
+     --eval-command "python examples/simple-mlx/evaluate.py --solution-path examples/simple-mlx/optimize.py" \
+     --metric speedup \
+     --maximize true \
+     --steps 30 \
+     --model o3-mini \
+     --additional-instructions examples/simple-mlx/metal-examples.rst
+```
+
+---
+
+### Command Line Arguments
+
+| Argument                    | Description                                                                                                                                                              | Required |
+| :-------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------- |
+| `--source`                  | Path to the source code file that will be optimized (e.g., `optimize.py`).                                                                                               | Yes      |
+| `--eval-command`            | Command to run for evaluating the code in `--source`. This command should print the target `--metric` and its value to the terminal (stdout/stderr). See note below. | Yes      |
+| `--metric`                  | The name of the metric you want to optimize (e.g., 'accuracy', 'speedup', 'loss'). This metric name should match what's printed by your `--eval-command`.            | Yes      |
+| `--maximize`                | Whether to maximize (`true`) or minimize (`false`) the metric.                                                                                                           | Yes      |
+| `--steps`                   | Number of optimization steps (LLM iterations) to run.                                                                                                                    | Yes      |
+| `--model`                   | Model identifier for the LLM to use (e.g., `gpt-4o`, `claude-3.5-sonnet`). Recommended models to try include `o3-mini`, `claude-3-haiku`, and `gemini-2.5-pro-exp-03-25`.        | Yes      |
+| `--additional-instructions` | (Optional) Natural language description of specific instructions OR path to a file containing detailed instructions to guide the LLM.                                       | No       |
+
+---
+
+
+
+### Important Note on Evaluation
+
+The command specified by `--eval-command` is crucial. It's responsible for executing the potentially modified code from `--source` and assessing its performance. **This command MUST print the metric you specified with `--metric` along with its numerical value to the terminal (standard output or standard error).** Weco reads this output to understand how well each code version performs and guide the optimization process.
+
+For example, if you set `--metric speedup`, your evaluation script (`eval.py` in the examples) should output a line like:
+
+```
+speedup: 1.5
+```
+
+or
+
+```
+Final speedup value = 1.5
+```
+
+Weco will parse this output to extract the numerical value (1.5 in this case) associated with the metric name ('speedup').
+
+
+## Contributing
+
+We welcome contributions! To get started:
+
+1.  **Fork and Clone the Repository:**
+    ```bash
+    git clone https://github.com/WecoAI/weco-cli.git
+    cd weco-cli
+    ```
+
+2.  **Install Development Dependencies:**
+    ```bash
+    pip install -e ".[dev]"
+    ```
+
+3.  **Create a Feature Branch:**
+    ```bash
+    git checkout -b feature/your-feature-name
+    ```
+
+4.  **Make Your Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
+
+5.  **Commit and Push** your changes, then open a pull request with a clear description of your enhancements.
+
+---

weco-0.2.3/PKG-INFO

@@ -1,141 +0,0 @@
-Metadata-Version: 2.4
-Name: weco
-Version: 0.2.3
-Summary: Documentation for `weco`, a CLI for using Weco AI's code optimizer.
-Author-email: Weco AI Team <dhruv@weco.ai>
-License: MIT
-Project-URL: Homepage, https://github.com/WecoAI/weco-cli
-Keywords: AI,Code Optimization,Code Generation
-Classifier: Programming Language :: Python :: 3
-Classifier: Operating System :: OS Independent
-Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.12
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: requests
-Requires-Dist: rich
-Provides-Extra: dev
-Requires-Dist: ruff; extra == "dev"
-Requires-Dist: build; extra == "dev"
-Requires-Dist: setuptools_scm; extra == "dev"
-Dynamic: license-file
-
-# Weco CLI – Code Optimizer for Machine Learning Engineers
-
-[![Python](https://img.shields.io/badge/Python-3.12.0-blue)](https://www.python.org)
-[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-
-`weco` is a command-line interface for interacting with Weco AI's code optimizer, powerred by [AI-Driven Exploration](https://arxiv.org/abs/2502.13138).
-
-
-
-https://github.com/user-attachments/assets/cb724ef1-bff6-4757-b457-d3b2201ede81
-
-
-
----
-
-## Overview
-
-The weco CLI leverages a tree search approach with LLMs to iteratively improve your code.
-
-![image](https://github.com/user-attachments/assets/a6ed63fa-9c40-498e-aa98-a873e5786509)
-
-
-
----
-
-## Setup
-
-1. **Install the Package:**
-
-   ```bash
-   pip install weco
-   ```
-
-2. **Configure API Keys:**
-
-   Set the appropriate environment variables for your language model provider:
-   
-   - **OpenAI:** `export OPENAI_API_KEY="your_key_here"`
-   - **Anthropic:** `export ANTHROPIC_API_KEY="your_key_here"`
-   - **Google DeepMind:** `export GEMINI_API_KEY="your_key_here"`
-
----
-
-## Usage
-
-### Command Line Arguments
-
-| Argument                    | Description                                                                                                                                   | Required |
-|-----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|----------|
-| `--source`                  | Path to the Python source code that will be optimized (e.g. optimize.py).                                                                     | Yes      |
-| `--eval-command`            | Command to run for evaluation (e.g. 'python eval.py --arg1=val1').                                                                            | Yes      |
-| `--metric`                  | Metric to optimize.                                                                                                                           | Yes      |
-| `--maximize`                | Whether to maximize ('true') or minimize ('false') the metric.                                                                                | Yes      |
-| `--steps`                   | Number of optimization steps to run.                                                                                                          | Yes      |
-| `--model`                   | Model to use for optimization.                                                                                                                | Yes      |
-| `--additional-instructions` | (Optional) Description of additional instructions OR path to a file containing additional instructions.                                       | No       |
-
----
-
-### Example
-
-Optimizing common operations in pytorch:
-```bash
-weco --source examples/simple-torch/optimize.py \
-     --eval-command "python examples/simple-torch/evaluate.py --solution-path examples/simple-torch/optimize.py --device mps" \
-     --metric speedup \
-     --maximize true \
-     --steps 15 \
-     --model "o3-mini" \
-     --additional-instructions "Fuse operations in the forward method while ensuring the max float deviation remains small. Maintain the same format of the code."
-```
-
-Optimizing these same using mlx and metal:
-```bash
-weco --source examples/simple-mlx/optimize.py \
-     --eval-command "python examples/simple-mlx/evaluate.py --solution-path examples/simple-mlx/optimize.py" \
-     --metric speedup \
-     --maximize true \
-     --steps 30 \
-     --model "o3-mini" \
-     --additional-instructions "examples/simple-mlx/metal-examples.rst"
-```
----
-
-## Supported Providers
-
-The CLI supports the following model providers:
-
-- **OpenAI:** Set your API key using `OPENAI_API_KEY`.
-- **Anthropic:** Set your API key using `ANTHROPIC_API_KEY`.
-- **Google DeepMind:** Set your API key using `GEMINI_API_KEY`.
-
----
-
-## Contributing
-
-We welcome contributions! To get started:
-
-1. **Fork and Clone the Repository:**
-   ```bash
-   git clone https://github.com/WecoAI/weco-cli.git
-   cd weco-cli
-   ```
-
-2. **Install Development Dependencies:**
-   ```bash
-   pip install -e ".[dev]"
-   ```
-
-3. **Create a Feature Branch:**
-   ```bash
-   git checkout -b feature/your-feature-name
-   ```
-
-4. **Make Your Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
-
-5. **Commit and Push** your changes, then open a pull request with a clear description of your enhancements.
-
----

weco-0.2.3/README.md

@@ -1,119 +0,0 @@
-# Weco CLI – Code Optimizer for Machine Learning Engineers
-
-[![Python](https://img.shields.io/badge/Python-3.12.0-blue)](https://www.python.org)
-[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-
-`weco` is a command-line interface for interacting with Weco AI's code optimizer, powerred by [AI-Driven Exploration](https://arxiv.org/abs/2502.13138).
-
-
-
-https://github.com/user-attachments/assets/cb724ef1-bff6-4757-b457-d3b2201ede81
-
-
-
----
-
-## Overview
-
-The weco CLI leverages a tree search approach with LLMs to iteratively improve your code.
-
-![image](https://github.com/user-attachments/assets/a6ed63fa-9c40-498e-aa98-a873e5786509)
-
-
-
----
-
-## Setup
-
-1. **Install the Package:**
-
-   ```bash
-   pip install weco
-   ```
-
-2. **Configure API Keys:**
-
-   Set the appropriate environment variables for your language model provider:
-   
-   - **OpenAI:** `export OPENAI_API_KEY="your_key_here"`
-   - **Anthropic:** `export ANTHROPIC_API_KEY="your_key_here"`
-   - **Google DeepMind:** `export GEMINI_API_KEY="your_key_here"`
-
----
-
-## Usage
-
-### Command Line Arguments
-
-| Argument                    | Description                                                                                                                                   | Required |
-|-----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|----------|
-| `--source`                  | Path to the Python source code that will be optimized (e.g. optimize.py).                                                                     | Yes      |
-| `--eval-command`            | Command to run for evaluation (e.g. 'python eval.py --arg1=val1').                                                                            | Yes      |
-| `--metric`                  | Metric to optimize.                                                                                                                           | Yes      |
-| `--maximize`                | Whether to maximize ('true') or minimize ('false') the metric.                                                                                | Yes      |
-| `--steps`                   | Number of optimization steps to run.                                                                                                          | Yes      |
-| `--model`                   | Model to use for optimization.                                                                                                                | Yes      |
-| `--additional-instructions` | (Optional) Description of additional instructions OR path to a file containing additional instructions.                                       | No       |
-
----
-
-### Example
-
-Optimizing common operations in pytorch:
-```bash
-weco --source examples/simple-torch/optimize.py \
-     --eval-command "python examples/simple-torch/evaluate.py --solution-path examples/simple-torch/optimize.py --device mps" \
-     --metric speedup \
-     --maximize true \
-     --steps 15 \
-     --model "o3-mini" \
-     --additional-instructions "Fuse operations in the forward method while ensuring the max float deviation remains small. Maintain the same format of the code."
-```
-
-Optimizing these same using mlx and metal:
-```bash
-weco --source examples/simple-mlx/optimize.py \
-     --eval-command "python examples/simple-mlx/evaluate.py --solution-path examples/simple-mlx/optimize.py" \
-     --metric speedup \
-     --maximize true \
-     --steps 30 \
-     --model "o3-mini" \
-     --additional-instructions "examples/simple-mlx/metal-examples.rst"
-```
----
-
-## Supported Providers
-
-The CLI supports the following model providers:
-
-- **OpenAI:** Set your API key using `OPENAI_API_KEY`.
-- **Anthropic:** Set your API key using `ANTHROPIC_API_KEY`.
-- **Google DeepMind:** Set your API key using `GEMINI_API_KEY`.
-
----
-
-## Contributing
-
-We welcome contributions! To get started:
-
-1. **Fork and Clone the Repository:**
-   ```bash
-   git clone https://github.com/WecoAI/weco-cli.git
-   cd weco-cli
-   ```
-
-2. **Install Development Dependencies:**
-   ```bash
-   pip install -e ".[dev]"
-   ```
-
-3. **Create a Feature Branch:**
-   ```bash
-   git checkout -b feature/your-feature-name
-   ```
-
-4. **Make Your Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
-
-5. **Commit and Push** your changes, then open a pull request with a clear description of your enhancements.
-
----

weco-0.2.3/weco.egg-info/PKG-INFO

@@ -1,141 +0,0 @@
-Metadata-Version: 2.4
-Name: weco
-Version: 0.2.3
-Summary: Documentation for `weco`, a CLI for using Weco AI's code optimizer.
-Author-email: Weco AI Team <dhruv@weco.ai>
-License: MIT
-Project-URL: Homepage, https://github.com/WecoAI/weco-cli
-Keywords: AI,Code Optimization,Code Generation
-Classifier: Programming Language :: Python :: 3
-Classifier: Operating System :: OS Independent
-Classifier: License :: OSI Approved :: MIT License
-Requires-Python: >=3.12
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: requests
-Requires-Dist: rich
-Provides-Extra: dev
-Requires-Dist: ruff; extra == "dev"
-Requires-Dist: build; extra == "dev"
-Requires-Dist: setuptools_scm; extra == "dev"
-Dynamic: license-file
-
-# Weco CLI – Code Optimizer for Machine Learning Engineers
-
-[![Python](https://img.shields.io/badge/Python-3.12.0-blue)](https://www.python.org)
-[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-
-`weco` is a command-line interface for interacting with Weco AI's code optimizer, powerred by [AI-Driven Exploration](https://arxiv.org/abs/2502.13138).
-
-
-
-https://github.com/user-attachments/assets/cb724ef1-bff6-4757-b457-d3b2201ede81
-
-
-
----
-
-## Overview
-
-The weco CLI leverages a tree search approach with LLMs to iteratively improve your code.
-
-![image](https://github.com/user-attachments/assets/a6ed63fa-9c40-498e-aa98-a873e5786509)
-
-
-
----
-
-## Setup
-
-1. **Install the Package:**
-
-   ```bash
-   pip install weco
-   ```
-
-2. **Configure API Keys:**
-
-   Set the appropriate environment variables for your language model provider:
-   
-   - **OpenAI:** `export OPENAI_API_KEY="your_key_here"`
-   - **Anthropic:** `export ANTHROPIC_API_KEY="your_key_here"`
-   - **Google DeepMind:** `export GEMINI_API_KEY="your_key_here"`
-
----
-
-## Usage
-
-### Command Line Arguments
-
-| Argument                    | Description                                                                                                                                   | Required |
-|-----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------|----------|
-| `--source`                  | Path to the Python source code that will be optimized (e.g. optimize.py).                                                                     | Yes      |
-| `--eval-command`            | Command to run for evaluation (e.g. 'python eval.py --arg1=val1').                                                                            | Yes      |
-| `--metric`                  | Metric to optimize.                                                                                                                           | Yes      |
-| `--maximize`                | Whether to maximize ('true') or minimize ('false') the metric.                                                                                | Yes      |
-| `--steps`                   | Number of optimization steps to run.                                                                                                          | Yes      |
-| `--model`                   | Model to use for optimization.                                                                                                                | Yes      |
-| `--additional-instructions` | (Optional) Description of additional instructions OR path to a file containing additional instructions.                                       | No       |
-
----
-
-### Example
-
-Optimizing common operations in pytorch:
-```bash
-weco --source examples/simple-torch/optimize.py \
-     --eval-command "python examples/simple-torch/evaluate.py --solution-path examples/simple-torch/optimize.py --device mps" \
-     --metric speedup \
-     --maximize true \
-     --steps 15 \
-     --model "o3-mini" \
-     --additional-instructions "Fuse operations in the forward method while ensuring the max float deviation remains small. Maintain the same format of the code."
-```
-
-Optimizing these same using mlx and metal:
-```bash
-weco --source examples/simple-mlx/optimize.py \
-     --eval-command "python examples/simple-mlx/evaluate.py --solution-path examples/simple-mlx/optimize.py" \
-     --metric speedup \
-     --maximize true \
-     --steps 30 \
-     --model "o3-mini" \
-     --additional-instructions "examples/simple-mlx/metal-examples.rst"
-```
----
-
-## Supported Providers
-
-The CLI supports the following model providers:
-
-- **OpenAI:** Set your API key using `OPENAI_API_KEY`.
-- **Anthropic:** Set your API key using `ANTHROPIC_API_KEY`.
-- **Google DeepMind:** Set your API key using `GEMINI_API_KEY`.
-
----
-
-## Contributing
-
-We welcome contributions! To get started:
-
-1. **Fork and Clone the Repository:**
-   ```bash
-   git clone https://github.com/WecoAI/weco-cli.git
-   cd weco-cli
-   ```
-
-2. **Install Development Dependencies:**
-   ```bash
-   pip install -e ".[dev]"
-   ```
-
-3. **Create a Feature Branch:**
-   ```bash
-   git checkout -b feature/your-feature-name
-   ```
-
-4. **Make Your Changes:** Ensure your code adheres to our style guidelines and includes relevant tests.
-
-5. **Commit and Push** your changes, then open a pull request with a clear description of your enhancements.
-
----